A Review of Anthropic's Global Workspace Paper

·LessWrong··

The below is a public review Anthropic asked me to write for their new global workspace paper. I recommend at least skimming their paper first.TLDR:I think this is a fantastic paper - it presents compelling evidence for some kind of "cognitive space" in models, that is used as a "working memory" for intermediate variables during a forward pass, shows that J-Lens is a useful technique for accessing this space. I believe these key claims.I believe J-Lens will be a useful (but limited) tool in prac...

Read full article →

Related Articles

OpenWrt One – Open Hardware Router
peter_d_sherman · Hacker News · 5h ago
What Emily Bender meant by "stochastic parrots"
digital55 · Hacker News · 8h ago
Nintendo announces new product revisions in Europe with replaceable batteries
akyuu · Hacker News · 10h ago
Road to Elm 1.0
wolfadex · Hacker News · 11h ago
A global workspace in language models
in-silico · Hacker News · 5h ago